18546842. METHOD AND APPARATUS FOR VISUAL REASONING simplified abstract (Robert Bosch GmbH)

From WikiPatents
Revision as of 09:52, 11 June 2024 by Wikipatents (talk | contribs) (Creating a new page)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

METHOD AND APPARATUS FOR VISUAL REASONING

Organization Name

Robert Bosch GmbH

Inventor(s)

Bo Zhang of Beijing (CN)

Chongxuan Li of Beijing (CN)

Hang Su of Beijing (CN)

Jun Zhu of Beijing (CN)

Ke Su of Beijing (CN)

Siliang Lu of Shanghai (CN)

Ze Cheng of Shanghai (CN)

METHOD AND APPARATUS FOR VISUAL REASONING - A simplified explanation of the abstract

This abstract first appeared for US patent application 18546842 titled 'METHOD AND APPARATUS FOR VISUAL REASONING

The patent application describes a method for visual reasoning using a Probabilistic Generative Model (PGM) and a set of modules.

  • The method involves providing a network with sets of inputs and outputs based on visual information.
  • It determines a posterior distribution over combinations of modules through the PGM.
  • Domain knowledge is applied as posterior regularization constraints on the determined distribution.

Potential Applications:

  • Visual recognition systems
  • Image processing algorithms
  • Pattern recognition technologies

Problems Solved:

  • Enhancing visual reasoning capabilities
  • Improving accuracy in image analysis
  • Optimizing decision-making processes based on visual data

Benefits:

  • Increased efficiency in visual data processing
  • Enhanced accuracy in pattern recognition
  • Improved performance of visual recognition systems

Commercial Applications:

  • Visual search engines
  • Autonomous vehicles
  • Medical imaging technologies

Questions about Visual Reasoning: 1. How does the method improve decision-making processes based on visual information? 2. What are the key advantages of using a Probabilistic Generative Model in visual reasoning?

Frequently Updated Research: Stay updated on advancements in visual reasoning technologies and applications to leverage the latest innovations in the field.


Original Abstract Submitted

A method for visual reasoning. The method includes: providing a network with sets of inputs and sets of outputs, wherein each set of inputs of the sets of inputs mapping to one of a set of outputs corresponding to the set of inputs based on visual information on the set of inputs, and wherein the network comprising a Probabilistic Generative Model (PGM) and a set of modules; determining a posterior distribution over combinations of one or more modules of the set of modules through the PGM, based on the provided sets of inputs and sets of outputs; and applying domain knowledge as one or more posterior regularization constraints on the determined posterior distribution.